Personal Project: MPP-Qwen14B & MPP-Qwen-Next(Multimodal Pipeline Parallel based on Qwen-LM). Support [video/image/multi-image] {sft/conversations}. Don't let the poverty limit your imagination! Train your own 8B/14B LLaVA-training-like MLLM on RTX3090/4090 24GB.
349
stars
19
forks
source link
Support "image-pretrain+image&video sft" for MPPQwen7B-video(along with multi-turn and multi-image support) #20